From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution

arXiv:2604.15097 · cs.SE, cs.CL · Submitted 2026-04-16 · Read on arXiv

cs.SE, cs.CL

Submitted: 2026-04-16

Updated: 2026-09-17

Comments: Technical Report

Code: https://github.com/EvoMap/skill2gep

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 18× in this paper · explained in 2 episodes
• Abstraction — 6× in this paper · explained in 1 episode
• Core — 6× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Provenance — 5× in this paper · explained in 3 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Gene Evolution Protocol — 4× in this paper
• Accuracy — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Agent Memory — 2× in this paper · explained in 1 episode
• Agent Skills — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
• Memento-Skills: Let Agents Design Agents
• CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System
• Memp: Exploring Agent Procedural Memory
• AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
• TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
• UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
• MemEvolve: Meta-Evolution of Agent Memory Systems
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
• Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
• Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties